Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    URL paths and endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Other
    0.64
     Other
    0.62
     other
    0.61
    Pl
    0.60
     અન્ય
    0.60
     Otras
    0.60
    Box
    0.58
    Used
    0.58
     ব্যবহৃত
    0.57
     used
    0.56
    POSITIVE LOGITS
     logout
    0.86
     cashback
    0.82
    /:
    0.81
    /{
    0.81
    logout
    0.76
    /${
    0.75
    login
    0.75
     chatId
    0.74
    ⇵
    0.74
    ","/
    0.73
    Act Density 0.121%

    No Known Activations